Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2681 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0821. Min Act: -0.0000

Data Index: 1843844 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0817. Min Act: -0.0000

Data Index: 1172503 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0815. Min Act: -0.0000

Data Index: 531480 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0795. Min Act: 0.0000

Data Index: 1433595 (The Pile)

Max Activating Token Index: 900

Text #4

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0779. Min Act: 0.0000

Data Index: 1865557 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0773. Min Act: -0.0000

Data Index: 443618 (The Pile)

Max Activating Token Index: 111

Text #6

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0768. Min Act: -0.0000

Data Index: 1752576 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0746. Min Act: 0.0000

Data Index: 1419885 (The Pile)

Max Activating Token Index: 31

Text #8

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0739. Min Act: -0.0000

Data Index: 777752 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0737. Min Act: -0.0000

Data Index: 1488371 (The Pile)

Max Activating Token Index: 132

Text #10

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0706. Min Act: 0.0000

Data Index: 1016406 (The Pile)

Max Activating Token Index: 302

Text #11

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0728. Min Act: -0.0000

Data Index: 448723 (The Pile)

Max Activating Token Index: 43

Text #12

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0725. Min Act: -0.0000

Data Index: 212473 (The Pile)

Max Activating Token Index: 82

Text #13

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0722. Min Act: -0.0000

Data Index: 1257197 (The Pile)

Max Activating Token Index: 3

Text #14

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0718. Min Act: -0.0000

Data Index: 1796793 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0718. Min Act: -0.0000

Data Index: 643705 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0717. Min Act: 0.0000

Data Index: 466653 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0714. Min Act: -0.0000

Data Index: 1438481 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0713. Min Act: 0.0000

Data Index: 1215698 (The Pile)

Max Activating Token Index: 399

Text #19

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0694. Min Act: 0.0000

Data Index: 1446029 (The Pile)

Max Activating Token Index: 60